corruption on vhost-scsi-pci in qemu

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



I'm building out some testing of pNFS SCSI layouts. It would be convenient to test pNFS on a single host with several qemu VMs, so I am using LIO's vhost target and presenting that to guests with qemu's vhost-scsi-pci device.

I've used both a block and fileio backed LUN, and each time I run bonnie++ on a freshly created XFS in the guest I end up with some kind of corruption.

I can verify a write pattern on the entire LUN. If I provide the LUN to the host using an LIO loopback device, it completes the benchmark on the host.

Any ideas what I am doing wrong, or suggestions to test the LUN's IO from within the guest to find the problem?

o- / ................................................................................................................ [...] o- backstores ..................................................................................................... [...] | o- block ......................................................................................... [Storage Objects: 1] | | o- local_sp4 ..................................... [/dev/fedora-server/scsi_layout_dev (5.0GiB) write-thru activated] | o- fileio ........................................................................................ [Storage Objects: 1] | | o- local_file ............................................................. [/lio_file (5.0GiB) write-back activated] | o- pscsi ......................................................................................... [Storage Objects: 0] | o- ramdisk ....................................................................................... [Storage Objects: 0] | o- user .......................................................................................... [Storage Objects: 0] o- iscsi ................................................................................................... [Targets: 0] o- loopback ................................................................................................ [Targets: 0] o- vhost ................................................................................................... [Targets: 1] o- naa.5001405c3c2282ec ..................................................................................... [TPGs: 1] o- tpg1 ......................................................................... [naa.50014057bb822c67, no-gen-acls] o- acls ................................................................................................. [ACLs: 0] o- luns ................................................................................................. [LUNs: 2] o- lun0 .................................................. [block/local_sp4 (/dev/fedora-server/scsi_layout_dev)] o- lun1 ......................................................................... [fileio/local_file (/lio_file)


I am using libvirt, adding this to my machine's config:

  <qemu:commandline>
    <qemu:arg value='-device'/>
<qemu:arg value='vhost-scsi-pci,id=scsi6,wwpn=naa.5001405c3c2282ec,event_idx=off'/>
  </qemu:commandline>

Thanks for any help,
Ben

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html



[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux